Sandeep Kshirsagar
London,United Kingdom
Summary
Accomplished professional with extensive expertise in Azure Machine Learnin and Generative AI. Proficient in deploying and monitoring machine learning models with a strong focus on Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). Demonstrated ability in LLM orchestration using LangChain and Semantic Kernel, alongside hands-on experience with Azure OpenAI Service. Skilled in time series forecasting, deep learning frameworks such as TensorFlow and PyTorch and managing data workflows using Databricks, MLflow and Kubeflow. Committed to leveraging advanced machine learning techniques to drive innovation and efficiency.
Overview
16
16
years of professional experience
1
1
Certification
Work history
Lead AI/ML Engineer
National Grid
Wokingham, United Kingdom
2022.08 - Current
- Deinged and delivered enterprise grade Azure MLOps platform for energy forecasting (PEF), which enabled rapid onboarding of new forecasting products including wind, solar and national demand.
- Cut model go-live time by ~55% by implementing reusable Azure ML python SDK v2 pipelines for data preparation, training, inference and environment promotion.
- Automated end-to-end ML lifecycle (ingestion, training, deployment, monitoring) using Azure DevOps CI/CD with controlled promotion across Dev, Staging and Production environments.
- Developed LLM + RAG conversational interface on Azure, which enabled business users to query forecasts interactively.
- Built LLM-driven report generation pipelines using AI Foundry and Databricks which automatically produces summaries from structured and unstructured forecast data.
British Telecommunications (BT Group)
AI& ML Engineer
Birmingham, United Kingdom
2021.12 - 2022.08
- Developed knowledge Extraction pipeline for large-scale text corpus with Semantic Extraction using pretrained T5 model, BERT word-sense disambiguation(WSD) and Constituent Parsing with AllenNLP.
- Optimized T5 model to reduce model size by 3x and increase the inference speed up-to 5x by converting into ONNX and quantize using FastT5 library.
- Deployed CSIM (customer service insight and management) ML multiple multivariate timeseries model which help identify the expensive customer journeys to Openreach and Proactively intervene them, resulted into £11m cost saving.
TechMahindra
Lead Data Scientist
Location: Birmingham, United Kingdom
2019.06 - 2021.12
- Implemented and deployed a Hot Start Predictor Model to forecast the cooling trajectory for each turbine shutdown, utilizing historical PI data. This led to a notable improvement in accuracy and a significant financial gain.
- Developed energy Consumption Forecasting model using Prophet to segment customers based on their energy consumption patterns and to forecast future energy consumption. The use of Prophet resulted in a 8% improvement in accuracy compared to traditional methods.
- Designed and developed a product recommendation engine which resulted in an 10% increase in click-through rate (CTR).
Virtusa
Senior Data Scientist
Location : Hyderabad, India
2018.09 - 2019.05
- Automated the process of directing the customer issues to the respective development team to increase revenue by 20%.
- Automated ML models deployment using Azure CI/CD pipelines and monitored the data drift in production.
Medtronic
Software Engineer II
Location : Hyderabad, India
2015.07 - 2018.09
- Built ML classifier to identify defective piece of signia handle produced during manufacturing using product images.
- Analyzed the reload transactions data and designed an analytical framework that will help customer to identify segments of customers based on the reload usage and, further classify the customers based on the segments.
Rockwell Collins
Tech Lead
Location : Hyderabad, India
2009.09 - 2015.07
- Developed Hmap multithreaded display application using C++ POSIX library on Green Hills Integrity RTOS .
Education
Bachelor's - Computer Science
SGGSI&ET, India
PG Diploma - AI and ML
Carnegie Mellon University
USASkills
- Azure Machine Learning (SDK v2)
- Azure AI Foundry
- Prompt Flow
- Retrieval-Augmented Generation (RAG)
- Azure OpenAI Service
- LLM Orchestration (LangChain / Semantic Kernel)
- Model Deployment & Monitoring
- Databricks Jobs API & Workflows
- Databrick Asset Bundles
- Time Series Forecasting
- PySpark
- MLflow
- TensorFlow
- PyTorch
- Kubeflow
- Azure DevOps (CI/CD)
Certification
- Microsoft certified Azure Data Scientist
- Google Cloud Certified Professional Data Engineer
Timeline
Lead AI/ML Engineer
National Grid
2022.08 - Current
British Telecommunications (BT Group)
AI& ML Engineer
2021.12 - 2022.08
TechMahindra
Lead Data Scientist
2019.06 - 2021.12
Virtusa
Senior Data Scientist
2018.09 - 2019.05
Medtronic
Software Engineer II
2015.07 - 2018.09
Rockwell Collins
Tech Lead
2009.09 - 2015.07
Bachelor's - Computer Science
SGGSI&ET, India
PG Diploma - AI and ML
Carnegie Mellon University